🚀 BLIP:用于统一视觉语言理解和生成的语言图像预训练引导
BLIP是一个新的视觉语言预训练(VLP)框架,它能够灵活地迁移到视觉语言理解和生成任务中。本模型是经过微调的Salesforce BLIP大型图像字幕模型,尤其增加了回复长度,可用于图像字幕生成任务。
 |
图片来源于BLIP官方仓库 |
📚 详细文档
论文 BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation 的作者在摘要中写道:
视觉语言预训练(VLP)提升了许多视觉语言任务的性能。然而,大多数现有的预训练模型仅在基于理解的任务或基于生成的任务中表现出色。此外,性能的提升主要是通过扩大从网络收集的带有噪声的图像文本对数据集来实现的,而网络数据是一种次优的监督来源。在本文中,我们提出了BLIP,一个新的VLP框架,它可以灵活地迁移到视觉语言理解和生成任务中。BLIP通过引导字幕有效地利用了有噪声的网络数据,其中一个字幕生成器生成合成字幕,一个过滤器去除有噪声的字幕。我们在广泛的视觉语言任务中取得了最先进的结果,如图像文本检索(平均召回率@1提高了2.7%)、图像字幕生成(CIDEr提高了2.8%)和视觉问答(VQA分数提高了1.6%)。BLIP在以零样本方式直接迁移到视频语言任务时也表现出了很强的泛化能力。代码、模型和数据集已发布。
💻 使用示例
你可以使用此模型进行条件和无条件的图像字幕生成。
基础用法
使用PyTorch模型
在CPU上运行模型
点击展开
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
在GPU上运行模型
全精度运行
点击展开
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
半精度(float16
)运行
点击展开
import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", torch_dtype=torch.float16).to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
📄 许可证
本模型使用的许可证为BSD 3条款许可证(BSD-3-Clause)。
📖 BibTex引用信息
@misc{https://doi.org/10.48550/arxiv.2201.12086,
doi = {10.48550/ARXIV.2201.12086},
url = {https://arxiv.org/abs/2201.12086},
author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}